What should a classifier system learn?

T Kovacs

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

12 Citations (Scopus)


We consider the issues of how a classifier system should learn to represent a Boolean function, and how we should measure its progress in doing so. We identify four properties which may be desirable of a representation; that it be complete, accurate, minimal and non-overlapping, and distinguish variations on two of these properties for the XCS system. We distinguish two categories of learning metric, introduce new metrics and evaluate them. We demonstrate the superiority of population state metrics over performance metrics in two situations, and in the process find evidence of XCS's strong bias against overlapping rules.
Translated title of the contributionWhat should a classifier system learn?
Original languageEnglish
Title of host publicationUnknown
EditorsJong-Hwan Kim
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages775 - 782
Number of pages7
Publication statusPublished - May 2001

Bibliographical note

Conference Proceedings/Title of Journal: Proceedings of the 2001 Congress on Evolutionary Computation (CEC)


Dive into the research topics of 'What should a classifier system learn?'. Together they form a unique fingerprint.

Cite this